Postprint version. Published in Proceedings of the Fourth Annual IEEE Symposium: Baltimore, MD, May 12, 1991, pages 170-177.
Copyright © 1991 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The definitive version is available at http://dx.doi.org/10.1109/CBMS.1991.128961.
NOTE: At the time of publication, the author Erika Rogers was not yet affiliated with Cal Poly.
The concept of Visual Interaction is introduced as the process which links perception and problem-solving such that problem-solving is affected by what is seen, and conversely, what is seen and perceived is affected by the current state of the problem-solving process. This paper describes the development of a cognitively-based model of the visual interaction process in diagnostic radiology, and shows how aspects of this model are being incorporated into the design and implementation of an intelligent computer-based radiological assistant. In order to achieve this, it is necessary to extract information about the nature and type of knowledge involved in this process, and then to determine how that knowledge is used to accomplish the task of radiological diagnosis.